This repository contains the official PyTorch implementation for "Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading". This paper has been accepted by British Machine Vision Conference (BMVC) 2019. If you find the paper or the code useful, please cite our paper:
@article{Weng2019_lipreading,
archivePrefix = {arXiv},
arxivId = {1905.02540},
author = {Weng, Xinshuo and Kitani, Kris},
eprint = {1905.02540},
journal = {BMVC},
title = {{Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading}},
url = {https://bmvc2019.org/wp-content/uploads/papers/0016-paper.pdf},
year = {2019}
}
2019/09/15, we are trying to release the code soon.